Skip to content

v0.80.6

Latest

Choose a tag to compare

@github-actions github-actions released this 18 Jun 20:00
· 17 commits to main since this release
Immutable release. Only release title and notes can be modified.

Added

  • Added read-only interactive /mcp and /skills inventory panels that expose configured runtime resources without displaying secret environment values.
  • Added Harness Control Plane V2 primitives: tamper-evident event ledger V2, replay verification, transaction coordinator, and runtime transaction integration for auditable state changes.
  • Added spec-kit compiler and verification commands (spec:check, spec:compile, spec:verify) with replay gates for validating harness-control specs before release.
  • Added source-backed public hooks fail-closed primitives for the ./hooks export.
  • Added containerization documentation and a Gondolin extension example for routing built-in tools into a local micro-VM.
  • Added Ant Ling provider selection and setup documentation.
  • Added NVIDIA NIM provider selection, setup documentation, and direct NIM request attribution headers.
  • Added ctx.mode to extension contexts so extensions can distinguish TUI, RPC, JSON, and print mode.
  • Added ctx.getSystemPromptOptions() for extension commands to inspect the current base system prompt inputs.
  • The interactive control footer now shows sampled process CPU% and RSS memory (width-adaptive segment).
  • Two new built-in themes omk-control and omk-control-light.
  • The working loader now exposes the model thinking level while streaming.

Changed

  • Changed auto-compaction summarizer inputs to use deterministic token-budget packing, semantic dependency closure, emergency handoff generation, and summary contract repair before returning compacted context.
  • Changed interactive model, theme, thinking-level, and editor keybinding paths to route through scoped transaction/keybinding flows with rollback-safe failure handling.
  • Changed internal runtime package dependencies to OMK-scoped packages and publish them before open-multi-agent-kit so installed omk can resolve its runtime imports.
  • Changed published coding-agent package metadata and source config defaults to use OMK/Open Multi-Agent Kit names, omkConfig, .omk, and the OMK repository.
  • 256-color theme quantization generalizes the cube/grayscale selection for near-neutral colors (colors with channel spread < 10 keep byte-identical output).

Fixed

  • Fixed Bun binary package asset resolution when OMK_PACKAGE_DIR points at a source or package layout instead of the extracted binary asset layout.
  • Fixed agent-session regression tests to use the workspace faux provider stream directly, keeping source-run tests aligned with dynamic provider registration while preserving built runtime behavior.
  • Fixed auto-compaction to trigger before provider requests when the projected prompt would exceed the configured context headroom.
  • Fixed temporary extension package installs to use a private ~/.omk/agent/tmp/extensions directory with 0700 permissions instead of a shared OS temp extension directory.
  • Fixed git package source handling to reject unsafe host/path components and keep managed clone paths inside install roots.
  • Fixed stored XSS in HTML session exports by sanitizing Markdown link and image URLs with a scheme allow-list after stripping control characters.
  • Fixed SDK embedding in bundled Node apps failing with ENOENT when package.json is not present next to the bundle entrypoint. The package metadata reader now gracefully handles missing package.json by using defaults, enabling createAgentSession() without requiring package-adjacent files at runtime (#5226).
  • Fixed HTTP timeout setting not being respected for non-Codex providers (e.g., llama.cpp via OpenAI-compatible API). The httpIdleTimeoutMs setting (set via /settings HTTP timeout) now applies as the default SDK request timeout for all providers that support it, not just OpenAI Codex Responses. Disabling the timeout (HTTP timeout = false) now correctly disables SDK timeouts for all supported providers by sending a maximum int32 value (effectively infinite) instead of 0, since SDKs treat timeout=0 as an immediate timeout (#5294).
  • Fixed opening and listing very large JSONL session files by reading session entries line-by-line instead of materializing the full file as one string (#5231).
  • Fixed renderShell: "self" tool renderers that emit no component lines leaving a blank chat row (#5299).